VIS Assignment-1
Jiwon Park
2020 9 8
library(ggplot2)
library(tidycensus)
library(tidyverse)
library(dplyr)
library(viridis)Variables Used
area_vars_2018 <- load_variables (2018, "acs5")- Total population (continuous) : tot_pop
- Median Income (continuous) : med_income
- Monthly Housing Cost (continuous) : mon_hous
- Percentage of the tenant population (continuous) : pct_ten
- Percentage of the population using public transport to work (continuous) : pct_pubtra
- Majority race of the population (not Hispanic or Latino) (categorical) : maj_race
- Whether the majority of the population is US-born or not (categorical) : maj_citizenship
Loading 2014-2018 5 year ACS data for Los Angeles county, CA
pop_vars <- c(tot_pop = "B01003_001",
med_income = "B21004_001",
mon_hous = "B25104_001",
tot_ten = "B07013_003",
tot_pubtra = "B08006_008",
white_alone = "B03002_003",
black_AA_alone = "B03002_004",
asian_alone = "B03002_006",
hispanic_latino = "B03002_012",
other = "B03002_008",
us_born = "B05001_002")
tractLA2018 <- get_acs(geography = "tract",
variables = pop_vars,
output = "wide",
state = "CA",
county = "Los Angeles",
year = 2018,
survey = "acs5")Calculating Variables
tractLA2018 <- tractLA2018 %>%
mutate(pct_ten = tot_tenE / tot_popE,
pct_pubtra = tot_pubtraE / tot_popE,
pct_white = white_aloneE/tot_popE,
pct_black = black_AA_aloneE/tot_popE,
pct_hisp_lat = hispanic_latinoE/tot_popE,
pct_asian = asian_aloneE/tot_popE,
pct_other = otherE/tot_popE,
maj_usborn = us_bornE / tot_popE) %>%
mutate(maj_race = case_when(pct_white > 0.5 ~ "nh_white",
pct_black > 0.5 ~ "nh_black",
pct_asian > 0.5 ~ "nh_asian",
pct_hisp_lat > 0.5 ~ "hs_latino",
pct_other > 0.5 ~ "nh_other",
TRUE ~ "no_majority")) %>%
mutate(maj_citizenship = case_when(maj_usborn > 0.5 ~ "usborn",
maj_usborn < 0.5 ~ "immigrant")) %>%
select(tot_popE, med_incomeE, mon_housE, pct_ten, pct_pubtra, maj_race, maj_citizenship)
tractLA2018## # A tibble: 2,346 x 7
## tot_popE med_incomeE mon_housE pct_ten pct_pubtra maj_race maj_citizenship
## <dbl> <dbl> <dbl> <dbl> <dbl> <chr> <chr>
## 1 5619 32500 1820 0.157 0.0114 nh_black usborn
## 2 4424 29242 1390 0.485 0.00475 hs_latino usborn
## 3 7441 26467 1886 0.193 0.0188 hs_latino usborn
## 4 8192 38699 2318 0.308 0 hs_latino usborn
## 5 7311 42620 2208 0.275 0.0146 hs_latino usborn
## 6 3742 28333 1334 0.622 0.0102 no_majority usborn
## 7 3846 23549 1469 0.650 0.0109 no_majority usborn
## 8 3908 25980 1572 0.495 0.0251 no_majority usborn
## 9 4914 37529 1575 0.162 0.00387 no_majority usborn
## 10 3562 45625 1530 0.608 0.0101 nh_white usborn
## # … with 2,336 more rowsPlot1
Plotting a majority of my variables
tractLA2018 <- tractLA2018 %>%
filter(!is.na(maj_citizenship))
ggplot(tractLA2018,
aes(x = med_incomeE,
y = pct_ten,
shape = maj_citizenship,
color = maj_race,
alpha = mon_housE)) +
geom_point(size = 1.3) +
scale_x_continuous(name = "Median Income",
breaks = seq(10000, 120000, by = 20000),
labels = c("10k","30k","50k","70k","90k","110k")) +
scale_y_continuous(name = "Percentage of Tenant population",
breaks = seq(0, 1, by = 0.1),
labels = paste(seq(0, 100, by = 10), "%", sep = "")) +
scale_color_discrete(name = "Majority race/ethnicity",
labels = c("Non-Hispanic White",
"Non-Hispanic Black",
"Hispanic Latino",
"Non-Hispanic Asian",
"Non-Hispanic Others",
"No Majority")) +
scale_alpha_continuous(name = "Monthly Housing Cost") +
scale_shape(name = "Majority Citizenship",
labels = c("US-Born", "Immigrant")) +
theme_bw() +
theme(legend.key.size = unit(0.1, "cm"))## Warning: Removed 7 rows containing missing values (geom_point).
Plot2
A scatter plot of median income and percentage of the tenant population.
theme_set(theme_classic())
ggplot(tractLA2018,
aes(x = pct_ten,
y = med_incomeE,
alpha = pct_pubtra)) +
stat_smooth(color = "red", linetype = 2, size = 0.7) +
geom_point(size = 0.7,color = "#271774") +
scale_alpha_continuous(name = "Percentage of Using Public Transport to Work") +
scale_x_continuous(name = "Percentage of Tenant population",
breaks = seq(0, 1, by = 0.1),
labels = paste(seq(0, 100, by = 10), sep = "")) +
scale_y_continuous(name = "Median Income",
breaks = seq(10000, 120000, by = 10000)) +
theme_linedraw() +
theme(text = element_text(size = 10),
legend.key.size = unit(0.5, "cm"))## Warning: Removed 7 rows containing non-finite values (stat_smooth).## Warning: Removed 7 rows containing missing values (geom_point).
Plot3
A heat map of majority citizenship and majority race/ethnicity.
tractLA2018 <- tractLA2018 %>%
filter(!is.na(maj_citizenship))
ggplot(tractLA2018,
aes(x = maj_race,
y = maj_citizenship,
fill = pct_ten,
na.rm = TRUE)) +
geom_tile() +
scale_x_discrete(name = "Majority Race/Ethnicity",
labels = c("Non-H White",
"Non-H Black",
"H Latino",
"Non-H Asian",
"Non-H Others",
"No Majority")) +
scale_y_discrete(name = "Majority Citizenship",
labels = c("US_Born",
"Immigrant")) +
scale_fill_distiller(palette = "#468966") +
labs(fill = "Percent of Tenant Population") +
theme_classic() +
theme(text = element_text(size = 10))## Warning in pal_name(palette, type): Unknown palette #468966
Plot4
Scatter plot of median income and the percent of tenant population
ggplot(tractLA2018, aes(x=pct_ten, y=med_incomeE, fill = maj_race)) +
geom_point(alpha=0.5, shape=21, color = "red") +
geom_smooth(method="loess", se=F, color = "#510E80") +
scale_fill_viridis(discrete=TRUE, guide=FALSE, option="B") +
scale_x_continuous(name = "Percentage of Tenant Population",
breaks = seq(0, 1, by = 0.1),
labels = paste(seq(0, 100, by = 10), "%", sep = "")) +
scale_y_continuous(name = "Median Income",
breaks = seq(10000, 120000, by = 10000),
labels = paste(seq(10, 120, by = 10), "K", sep = "")) +
labs(fill = "Majority Race/Ethnicity") ## `geom_smooth()` using formula 'y ~ x'## Warning: Removed 7 rows containing non-finite values (stat_smooth).## Warning: Removed 7 rows containing missing values (geom_point).
Plot5
Scatterplot with a polar coordinate system of the percentage of tenant population and the percentage of using public transport to work
theme_set(theme_bw())
ggplot(tractLA2018,
aes(x = pct_pubtra,
y = pct_ten)) +
geom_point(alpha = 0.5, size = 0.5) +
stat_smooth(color = "red", linetype = 2, size = 1) +
scale_y_continuous(name = "Percentage of Tenant Population",
breaks = seq(0, 1, by = 0.2),
labels = paste(seq(0, 100, by = 20), sep = "")) +
scale_x_continuous(name = "Percentage of Using Public Transportation to Work",
breaks = seq(0, 1, by = 0.1),
labels = paste(seq(0, 100, by = 10), sep = "")) +
coord_polar(theta = "x") ## `geom_smooth()` using method = 'gam' and formula 'y ~ s(x, bs = "cs")'
Plot6
A dot plot of the percent of using public transportation to work and majority race/ethnicity
theme_set(theme_gray())
ggplot(tractLA2018,
aes(x = maj_race,
y = pct_pubtra,
color = maj_race)) +
geom_point(size = 0.8,
alpha = 0.5) +
scale_x_discrete(name = "Majority Race/Ethnicity",
labels = c("Non-H White", "Non-H Black", "Non-H Asian", "H Latino", "Non-H Other", "No Majority")) +
scale_y_continuous(name = "Percentage of Using Public Transportation to Work",
breaks = seq(0, 1, by = 0.1),
labels = paste(seq(0, 100, by = 10), sep = "")) +
theme(legend.position = "none")
Plot7
A dot plot with jitter of the percent of tenant population and majority race/ethnicity
theme_set(theme_light())
ggplot(tractLA2018,
aes(x = maj_race,
y = pct_ten,
color = maj_race)) +
geom_point(position = "jitter",
size = 0.5,
alpha = 0.7) +
scale_x_discrete(name = "Majority Race/Ethnicity",
labels = c("Non-H White", "Non-H Black", "Non-H Asian", "H Latino", "Non-H Other", "No Majority")) +
scale_y_continuous(name = "Percentage of Tenant Population",
breaks = seq(0, 1, by = 0.1),
labels = paste(seq(0, 100, by = 10), sep = "")) +
theme(legend.position = "none")
Plot8
A box plot of the percentage of tenant population and the majority race/ethnicity
theme_set(theme_dark())
ggplot(tractLA2018,
aes(x = maj_race,
y = pct_ten,
color = maj_race)) +
geom_boxplot() +
scale_x_discrete(name = "Majority Race/Ethnicity",
labels = c("Non-H White", "Non-H Black", "Non-H Asian", "H Latino", "Non-H Other", "No Majority")) +
scale_y_continuous(name = "Percentage of Tenant Population",
breaks = seq(0, 1, by = 0.1),
labels = paste(seq(0, 100, by = 10), sep = "")) +
theme(legend.position = "none")
Plot9
A violin plot of the percentage of tenant population and the majority race/ethnicity
ggplot(tractLA2018,
aes(x = maj_race,
y = pct_ten,
color = maj_race)) +
geom_violin() +
scale_fill_viridis(discrete=TRUE) +
scale_color_viridis(discrete=TRUE) +
geom_point(position = "jitter",
size = 0.3,
alpha = 0.7) +
scale_x_discrete(name = "Majority Race/Ethnicity",
labels = c("Non-H White", "Non-H Black", "Non-H Asian", "H Latino", "Non-H Other", "No Majority")) +
scale_y_continuous(name = "Percentage of Tenant Population",
breaks = seq(0, 1, by = 0.1),
labels = paste(seq(0, 100, by = 10), sep = "")) +
theme(legend.position = "none")
Plot10
Stacked bar chart of percentage of using public transportation to work and majority citizenship
theme_set(theme_classic())
tractLA2018 <- tractLA2018 %>%
filter(!is.na(maj_citizenship))
ggplot(tractLA2018,
aes(x=maj_citizenship, y=pct_pubtra, fill = maj_race)) +
geom_bar(stat = "identity", width = 0.5) +
scale_y_continuous(name = "Percentage of Using Public Transportation to Work") +
scale_x_discrete(name = "Majority Citizenship",
labels = c("US-Born",
"Immigrant"))
Plot11
Bar chart of number of tracts and majority citizenship
theme_set(theme_bw())
ggplot(tractLA2018, aes(x = maj_citizenship, fill = maj_race)) +
geom_bar(position = "dodge2") +
scale_y_continuous(name = "Number of Tracts") +
scale_x_discrete(name = "Majority Citizenship",
labels = c("US_born", "Immigrant")) +
scale_fill_discrete(name = element_blank(),
labels = c("Non-H White", "Non-H Black", "Non-H Asian", "H Latino", "Non-H Other", "No Majority")) +
labs(title= "") 
Plot12
Area chart of the percentage of tenant population
theme_set(theme_minimal())
ggplot(tractLA2018, aes(x=pct_ten)) +
geom_density(color="darkblue", fill="lightblue", alpha=0.8) +
scale_x_continuous(name = "Percentage of Tenant population ",
breaks = seq(0, 1, by = 0.1),
labels = paste(seq(0, 100, by = 10), "%", sep = "")) +
labs(title= "Percentage of Tenant Population of the census tracts in LA county") 
Plot13
Count Chart of the percentage of using public transport to work and majority race/ethnicity
theme_set(theme_minimal())
ggplot(tractLA2018, aes(x=maj_race, y=pct_pubtra)) +
geom_count(color="tomato3", show.legend=TRUE) +
scale_y_continuous(name = "Percentage of Using Public Transportation to Work",
breaks = seq(0, 1, by = 0.1),
labels = paste(seq(0, 100, by = 10), "%", sep = "")) +
scale_x_discrete(name = "Majority Race/Ethnicity",
labels = c("Non-H White", "Non-H Black", "Non-H Asian", "H Latino", "Non-H Other", "No Majority")) +
labs(title= "Percentage of Using Public Transport to Work by Major Race/Ethnicity",
subtitle = "Census tracts in LA county") 